Want to build your own Gemini-powered applications? Bring your laptops. This technical session provides the interactive experience you need. We’ll guide you through practical examples and code snippets, and cover how to start creating with the Gemini SDK on Vertex AI.

This session is a deep dive into strategies for maximizing the performance and efficiency of generative AI model training using Vertex AI and Cloud TPUs (Tensor Processing Units) and GPUs. You'll learn how to harness the power of Cloud TPUs and GPUs for accelerated training. Join our experts to learn more about best practices for configuring compute resources, selecting the ideal hardware for your use cases, and streamlining the overall model development process with Ray, Persistent Cluster, and shared reservations.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

Google AI and Vertex AI are two Google Cloud platforms that allow developers to access the Gemini API. In this session, developers will learn what is possible to do today, and they will see some sneak peeks about what is coming.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.

It can be challenging to know where and how to start building with Generative AI. Join this introductory workshop to learn about the tools and techniques needs to get started building with foundation models. We show you how to experiment with Gemini in the Cloud console and evaluate the performance of Gemini for your specific use case.

Click the blue “Learn more” button above to tap into special offers designed to help you implement what you are learning at Google Cloud Next 25.